Molecular Evolution of a Peptide GPCR Ligand Driven by Artificial Neural Networks

Peptide ligands of G protein-coupled receptors constitute valuable natural lead structures for the development of highly selective drugs and high-affinity tools to probe ligand-receptor interaction. Currently, pharmacological and metabolic modification of natural peptides involves either an iterative trial-and-error process based on structure-activity relationships or screening of peptide libraries that contain many structural variants of the native molecule. Here, we present a novel neural network architecture for the improvement of metabolic stability without loss of bioactivity. In this approach the peptide sequence determines the topology of the neural network and each cell corresponds one-to-one to a single amino acid of the peptide chain. Using a training set, the learning algorithm calculated weights for each cell. The resulting network calculated the fitness function in a genetic algorithm to explore the virtual space of all possible peptides. The network training was based on gradient descent techniques which rely on the efficient calculation of the gradient by back-propagation. After three consecutive cycles of sequence design by the neural network, peptide synthesis and bioassay this new approach yielded a ligand with 70fold higher metabolic stability compared to the wild type peptide without loss of the subnanomolar activity in the biological assay. Combining specialized neural networks with an exploration of the combinatorial amino acid sequence space by genetic algorithms represents a novel rational strategy for peptide design and optimization.

[1]  Gérard Dreyfus,et al.  Graph Machines and Their Applications to Computer-Aided Drug Design: A New Approach to Learning from Structured Data , 2006, UC.

[2]  Tsutomu Kouyama,et al.  Crystal structure of squid rhodopsin , 2008, Nature.

[3]  Gisbert Schneider,et al.  Design of MHC I stabilizing peptides by agent-based exploration of sequence space. , 2007, Protein engineering, design & selection : PEDS.

[4]  Jonathan D Hirst,et al.  Machine learning in virtual screening. , 2009, Combinatorial chemistry & high throughput screening.

[5]  Gebhard F. X. Schertler,et al.  Structure of a β1-adrenergic G-protein-coupled receptor , 2008, Nature.

[6]  K. Palczewski,et al.  Crystal Structure of Rhodopsin: A G‐Protein‐Coupled Receptor , 2002, Chembiochem : a European journal of chemical biology.

[7]  M. Parmentier,et al.  The C-terminal Nonapeptide of Mature Chemerin Activates the Chemerin Receptor with Low Nanomolar Potency* , 2004, Journal of Biological Chemistry.

[8]  S. Parlee,et al.  Serum chemerin levels vary with time of day and are modified by obesity and tumor necrosis factor-{alpha}. , 2010, Endocrinology.

[9]  H. Jacobe,et al.  Tazarotene-induced gene 2 (TIG2), a novel retinoid-responsive gene in skin. , 1997, The Journal of investigative dermatology.

[10]  E. Jacoby,et al.  The 7TM G-Protein-Coupled Receptor Target Family , 2006 .

[11]  Kuo-Chen Chou,et al.  Peptide reagent design based on physical and chemical properties of amino acid residues , 2007, J. Comput. Chem..

[12]  T. Kohonen Self-organized formation of topographically correct feature maps , 1982 .

[13]  J. Gutkind,et al.  G-protein-coupled receptors and signaling networks: emerging paradigms. , 2001, Trends in pharmacological sciences.

[14]  P. Zimmet,et al.  Chemerin is a novel adipokine associated with obesity and metabolic syndrome. , 2007, Endocrinology.

[15]  L. Cooper,et al.  When Networks Disagree: Ensemble Methods for Hybrid Neural Networks , 1992 .

[16]  P. Willett Genetic algorithms in molecular recognition and design. , 1995, Trends in biotechnology.

[17]  M. Burghammer,et al.  Crystal structure of the human β2 adrenergic G-protein-coupled receptor , 2007, Nature.

[18]  G. Schneider,et al.  Peptide design aided by neural networks: biological activity of artificial signal peptidase I cleavage sites. , 1998, Biochemistry.

[19]  Konstantin V. Balakin,et al.  Structure-Based versus Property-Based Approaches in the Design of G-Protein-Coupled Receptor-Targeted Libraries , 2003, J. Chem. Inf. Comput. Sci..

[20]  Andreas Schwienhorst,et al.  Thrombin inhibitors identified by computer-assisted multiparameter design. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[21]  Jörg D. Wichard,et al.  Computer Assisted Peptide Design and Optimization with Topology Preserving Neural Networks , 2010, ICAISC.

[22]  D. Greaves,et al.  Synthetic chemerin-derived peptides suppress inflammation through ChemR23 , 2008, The Journal of experimental medicine.

[23]  G Schneider,et al.  Artificial neural networks for computer-based molecular design. , 1998, Progress in biophysics and molecular biology.

[24]  James Devillers,et al.  Neural Networks in QSAR and Drug Design , 1996 .

[25]  J. van Leeuwen,et al.  Neural Networks: Tricks of the Trade , 2002, Lecture Notes in Computer Science.

[26]  Jonathan A. Javitch,et al.  Structure of the Human Dopamine D3 Receptor in Complex with a D2/D3 Selective Antagonist , 2010, Science.

[27]  Elie Bienenstock,et al.  Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[28]  Johann Gasteiger,et al.  Neural Networks for Chemists: An Introduction , 1993 .

[29]  S. Agatonovic-Kustrin,et al.  Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research. , 2000, Journal of pharmaceutical and biomedical analysis.

[30]  D. Greaves,et al.  Chemerin Peptides Promote Phagocytosis in a ChemR23- and Syk-Dependent Manner , 2010, The Journal of Immunology.

[31]  Matthew C. Ernst,et al.  Chemerin: at the crossroads of inflammation and obesity , 2010, Trends in Endocrinology & Metabolism.

[32]  R. Yoshimoto,et al.  Identification of a stable chemerin analog with potent activity toward ChemR23 , 2009, Peptides.

[33]  V. Hruby Designing peptide receptor agonists and antagonists , 2002, Nature Reviews Drug Discovery.

[34]  Klaus-Robert Müller,et al.  Efficient BackProp , 2012, Neural Networks: Tricks of the Trade.

[35]  Johann Gasteiger,et al.  Neural networks and genetic algorithms in drug design , 2001 .

[36]  Xiao-Yan Du,et al.  Proteolytic regulatory mechanism of chemerin bioactivity. , 2009, Acta biochimica et biophysica Sinica.

[37]  Johannes Schuchhardt,et al.  Adaptive encoding neural networks for the recognition of human signal peptide cleavage sites , 2000, Bioinform..

[38]  Ruben Abagyan,et al.  Structure of the human histamine H1 receptor complex with doxepin , 2011, Nature.

[39]  D. Greaves,et al.  Chemerin Contributes to Inflammation by Promoting Macrophage Adhesion to VCAM-1 and Fibronectin through Clustering of VLA-4 and VLA-5 , 2010, The Journal of Immunology.

[40]  Helgi B. Schiöth,et al.  Structural diversity of G protein-coupled receptors and significance for drug discovery , 2008, Nature Reviews Drug Discovery.

[41]  R. Abagyan,et al.  Structures of the CXCR4 Chemokine GPCR with Small-Molecule and Cyclic Peptide Antagonists , 2010, Science.

[42]  Edgar Jacoby,et al.  The 7 TM G‐Protein‐Coupled Receptor Target Family , 2006, ChemMedChem.

[43]  Thomas Lengauer,et al.  Automatic Generation of Complementary Descriptors with Molecular Graph Networks , 2005, J. Chem. Inf. Model..

[44]  Mina Okochi,et al.  Computationally assisted screening and design of cell-interactive peptides by a cell-based assay using peptide arrays and a fuzzy neural network algorithm. , 2008, BioTechniques.

[45]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[46]  J. Skolnick,et al.  Application of an artificial neural network to predict specific class I MHC binding peptide sequences , 1998, Nature Biotechnology.

[47]  K. Goralski,et al.  Chemerin exacerbates glucose intolerance in mouse models of obesity and diabetes. , 2010, Endocrinology.

[48]  W. Forssmann,et al.  Characterization of human circulating TIG2 as a ligand for the orphan receptor ChemR23 , 2003, FEBS letters.

[49]  Andreas Schwienhorst,et al.  Genetic algorithm for the design of molecules with desired properties , 2002, J. Comput. Aided Mol. Des..

[50]  B. Olde,et al.  Characterization of the human chemerin receptor--ChemR23/CMKLR1--as co-receptor for human and simian immunodeficiency virus infection, and identification of virus-binding receptor domains. , 2006, Virology.

[51]  Ah Chung Tsoi,et al.  The Graph Neural Network Model , 2009, IEEE Transactions on Neural Networks.

[52]  Håvard Jenssen,et al.  Serum stability of peptides. , 2008, Methods in molecular biology.

[53]  A. Roli Artificial Neural Networks , 2012, Lecture Notes in Computer Science.

[54]  E. Butcher,et al.  Regulation of Chemerin Bioactivity by Plasma Carboxypeptidase N, Carboxypeptidase B (Activated Thrombin-activable Fibrinolysis Inhibitor), and Platelets , 2009, Journal of Biological Chemistry.

[55]  E. Butcher,et al.  Chemerin, a Novel Adipokine That Regulates Adipogenesis and Adipocyte Metabolism* , 2007, Journal of Biological Chemistry.

[56]  宁北芳,et al.  疟原虫var基因转换速率变化导致抗原变异[英]/Paul H, Robert P, Christodoulou Z, et al//Proc Natl Acad Sci U S A , 2005 .

[57]  R. Stevens,et al.  The 2.6 Angstrom Crystal Structure of a Human A2A Adenosine Receptor Bound to an Antagonist , 2008, Science.

[58]  Xavier Llorà,et al.  Evolutionary combinatorial chemistry, a novel tool for SAR studies on peptide transport across the blood–brain barrier. Part 2. Design, synthesis and evaluation of a first generation of peptides , 2005, Journal of peptide science : an official publication of the European Peptide Society.

[59]  M. Maggiolini,et al.  G protein-coupled receptors: novel targets for drug discovery in cancer , 2010, Nature Reviews Drug Discovery.

[60]  G. Schneider,et al.  Peptide design by artificial neural networks and computer-based evolutionary search. , 1998, Proceedings of the National Academy of Sciences of the United States of America.

[61]  K. Fiedler,et al.  Neural Networks for Chemists (An Introduction) , 1995 .

[62]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[63]  Natalie Jäger,et al.  MHC I Stabilizing Potential of Computer-Designed Octapeptides , 2010, Journal of biomedicine & biotechnology.

[64]  W. Forssmann,et al.  Quantification of angiotensin-converting-enzyme-mediated degradation of human chemerin 145-154 in plasma by matrix-assisted laser desorption/ionization-time-of-flight mass spectrometry. , 2007, Analytical biochemistry.

[65]  S. V. Antonenko,et al.  HIV-1 reverse transcriptase inhibitor design using artificial neural networks. , 1994, Journal of medicinal chemistry.

[66]  Geoffrey J. Barton,et al.  Jalview Version 2—a multiple sequence alignment editor and analysis workbench , 2009, Bioinform..